Joan Colomer

Combining multiway principal component analysis (MPCA) and clustering for efficient data mining of historical data sets of SBR processes

A methodology based on Principal Component Analysis (PCA) and clustering is evaluated for process monitoring and process analysis of a pilot-scale SBR removing nitrogen and phosphorus. The first step of this method is to build a multi-way PCA (MPCA) model using the historical process data. In the second step, the principal scores and the Q-statistics resulting from the MPCA model are fed to the LAMDA clustering algorithm. This procedure is iterated twice. The first iteration provides an efficient and effective discrimination between normal and abnormal operational conditions. The second iteration of the procedure allowed a clear-cut discrimination of applied operational changes in the SBR history. Important to add is that this procedure helped identifying some changes in the process behaviour, which would not have been possible, had we only relied on visually inspecting this online data set of the SBR (which is traditionally the case in practice). Hence the PCA based clustering methodology is a promising tool to efficiently interpret and analyse the SBR process behaviour using large historical online data sets.

QUALITATIVE REPRESENTATION OF PROCESS TRENDS FOR SITUATION ASSESSMENT BASED ON CASES

Abstract Situation assessment in complex systems is often achieved by expert operators taking into account evolution of signals and comparing it with previous experiences. The criteria used by operators to compare actual situations with previous ones are not easily explainable and in fact they are part of the cognitive procedure. This paper proposes to use qualitative representations of signal trends as experienced cases. The work is centred in two main aspects. First, episodes based representation of signal trends proposed in the CHEM project is used as a description of cases. Then, a similarity criterion among signal representations is defined by a Dynamic Time Warping approach. The usefulness of the approach is shown in an illustrative example by representing and comparing signal dynamics with the goal of Situation Assessment.

Predicting aerodynamic instabilities in a blast furnace

This paper discusses the analysis of differential pressure signals in a blast furnace stack by using principal component analysis (PCA) and qualitative trend analysis (QTA) based on episodes. These methods can work jointly or separately and are applied using two toolboxes developed within the European CHEM project. The objective in this paper is to predict aerodynamic instability in a blast furnace with sufficient warning to enable the blast volume to be reduced in order to minimise that instability. Both methods based on signals and the expert knowledge provide an efficient approach to slip prediction. ^(C)xxx 2004. All rights reserved.

Expert supervision based on cases

The paper focuses on taking advantage of large amounts of data that are systematically stored in plants (by means of SCADA systems), but not exploited enough in order to achieve supervisory goals (fault detection, diagnosis and reconfiguration). The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial processes by re-using the stored data. The goal is to take advantage of experiences, registered in a suitable structure as cam, avoiding the tedious task of knowledge acquisition and representation needed by other reasoning techniques as expert systems. An outlook of CBR terminology and basic concepts are presented. The adaptation of CBR in performing expert supervisory tasks, taking into account the particularities and difficulties derived from dynamic systems, is discussed. A special interest is focused in proposing a general case definition suitable for supervisory tasks. Finally, this structure and the whole methodology is tested in a application example for monitoring a real drier chamber.

Extending a Fault Dictionary Towards a Case Based Reasoning System for Linear Electronic Analog Circuits Diagnosis

There are plenty of methods proposed for analog electronic circuit diagnosis, but the most popular ones are the fault dictionary techniques. Admitting more cases in a fault dictionary can be seen as a natural development towards a CBR system. The proposal of this paper is to extend the fault dictionary towards a Case Based Reasoning system. The case base memory, retrieval, reuse, revise and retain tasks are described. Special attention to the learning process is taken. An application example on a biquadratic filter is shown. The faults considered are parametric, permanent, independent and simple, although the methodology could be extrapolated for catastrophic and multiple fault diagnosis. Also, the method is focused and tested only on passive faulty components. Nevertheless, it can be extended to cover active devices as well.

A hybrid method for sag source location in power network

The work presented in this paper belongs to the power quality knowledge area and deals with the voltage sags in power transmission and distribution systems. Propagating throughout the power network, voltage sags can cause plenty of problems for domestic and industrial loads that can financially cost a lot. To impose penalties to responsible party and to improve monitoring and mitigation strategies, sags must be located in the power network. With such a worthwhile objective, this paper comes up with a new method for associating a sag waveform with its origin in transmission and distribution networks. It solves this problem through developing hybrid methods which hire multiway principal component analysis (MPCA) as a dimension reduction tool. MPCA reexpresses sag waveforms in a new subspace just in a few scores. We train some well-known classifiers with these scores and exploit them for classification of future sags. The capabilities of the proposed method for dimension reduction and classification are examined using the real data gathered from three substations in Catalonia, Spain. The obtained classification rates certify the goodness and powerfulness of the developed hybrid methods as brand-new tools for sag classification.

INFLUENCE OF SCALING AND UNFOLDING IN PCA BASED MONITORING OF NUTRIENT REMOVING BATCH PROCESS

Abstract The data set of batch biological and biotechnological processes can be organized in a three-way data matrix. In this paper the usefulness of different PCA approaches for monitoring is analyzed. Different ways of unfolding and scaling of data have been applied to a pilot-scale SBR data. PCA is used to reduce the dimensionality and to remove the non-linearity dynamic of the data. Moreover, a new method to select the number of principal components is proposed. Loadings graphics are used to determinate the predominant variables for each one. The results show that whatever model can be applied depending on the goal of the monitoring, however the models implicate possible false alarms or faults omission.

Embedding objects into Matlab/Simulink for process supervision

This paper introduces how artificial intelligence technologies can be integrated into a known computer aided control system design (CACSD) framework, Matlab/Simulink, using an object oriented approach. The aim is to build a framework to aid supervisory systems analysis, design and implementation. The idea is to take advantage of an existing CACSD framework, Matlab/Simulink, so that engineers can proceed: first to design a control system, and then to design a straightforward supervisory system of the control system in the same framework. Thus, expert systems and qualitative reasoning tools are incorporated into this popular CACSD framework to develop a computer aided supervisory system design (CASSD) framework. Object-variables an introduced into Matlab/Simulink for sharing information between tools.

QSSI: A NEW SIMILARITY INDEX FOR QUALITATIVE TIME SERIES. APPLICATION TO CLASSIFY VOLTAGE SAGS

This work is focused on defining and implementing a new similarity criterion for sequences of symbolic representations. The proposed algorithm returns a normalized index related to the degree of matching between sequences of qualitative labels. Performance of this method has been tested in the classification of voltage sags (transient reduction of voltage magnitude) gathered at 25 kV distribution substations. The objective is to assist monitoring systems in locating the origin of such disturbances in the transmission (HV) or distribution (MV) system. The promising classification accuracy achieved when this method was used with test data suggests that the presented algorithm could be applied satisfactorily and confirms its utility in classification approaches.

On-line oxygen uptake rate as a new tool for monitoring and controlling the SBR process

Abstract This paper focuses on the on-line Oxygen Uptake Rate (OUR) as a new tool for identifying the state of the plant during the aerobic phases of the SBR cycle and as a control parameter to optimize the SBR process. A real-time control system has been designed to adjust the aerobic phases length using on-line OUR as the endpoint of the aerobic phase. The control system implementation has permitted the aerobic phase length reduction around 11% implying significant savings in management costs.